INDEX

Explanations

references to leaders or leadership roles

oai_token-act-pair · gpt-3.5-turbo

the term "leader" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zl

-0.78

ighth

-0.74

Pwr

-0.71

agra

-0.69

ork

-0.67

elsius

-0.66

emale

-0.66

berra

-0.66

urious

-0.65

usion

-0.63

POSITIVE LOGITS

leader

1.03

boards

0.99

 leader

0.95

board

0.92

 negotiator

0.92

stand

0.86

pins

0.83

esses

0.83

pin

0.78

 scorer

0.78

Activations Density 0.020%

references to leaders or leadership roles

the term "leader" in various contexts

No Comments

No Known Activations